Index

A

action_dim (jax_agents.algorithms.ddpg.DDPGConfig attribute) (jax_agents.algorithms.ddpg.DDPGFunc attribute)

B

batch_size (jax_agents.common.training.TrainConfig attribute)

buffer_size (jax_agents.common.training.TrainConfig attribute)

C

check_if_done() (jax_agents.environments.pendulum.PendulumEnv method) close() (jax_agents.common.data_processor.DataProcessor method) (jax_agents.common.data_processor.EpisodeLogger method) (jax_agents.common.simulation.SimLogger method)

D

data_callback() (jax_agents.common.data_processor.DataProcessor method) DataProcessor (class in jax_agents.common.data_processor) DDPG (class in jax_agents.algorithms.ddpg)

DDPGConfig (class in jax_agents.algorithms.ddpg) DDPGFunc (class in jax_agents.algorithms.ddpg) DDPGState (class in jax_agents.algorithms.ddpg)

E

EpisodeLogger (class in jax_agents.common.data_processor)

G

gamma (jax_agents.algorithms.ddpg.DDPGConfig attribute) (jax_agents.algorithms.ddpg.DDPGFunc attribute)

I

initialize_rendering() (jax_agents.environments.pendulum.PendulumEnv method)

J

jax_agents.algorithms.ddpg (module) jax_agents.common.data_processor (module) jax_agents.common.networks (module) jax_agents.common.plotting (module)

jax_agents.common.runge_kutta (module) jax_agents.common.simulation (module) jax_agents.common.training (module) jax_agents.environments.pendulum (module)

L

learning_rate (jax_agents.algorithms.ddpg.DDPGConfig attribute) load() (jax_agents.algorithms.ddpg.DDPG class method)

log() (jax_agents.common.data_processor.EpisodeLogger method) (jax_agents.common.simulation.SimLogger method)

M

max_episode_len (jax_agents.common.training.TrainConfig attribute)

mlp_policy_net() (in module jax_agents.common.networks) mlp_value_net() (in module jax_agents.common.networks)

N

n_steps (jax_agents.common.training.TrainConfig attribute)

norm_state() (jax_agents.environments.pendulum.PendulumEnv method)

P

pendulum_dynamics() (jax_agents.environments.pendulum.PendulumEnv method) PendulumEnv (class in jax_agents.environments.pendulum) pi_net (jax_agents.algorithms.ddpg.DDPGFunc attribute) pi_net_size (jax_agents.algorithms.ddpg.DDPGConfig attribute)

pi_opt_state (jax_agents.algorithms.ddpg.DDPGState attribute) pi_optimizer (jax_agents.algorithms.ddpg.DDPGFunc attribute) pi_params (jax_agents.algorithms.ddpg.DDPGState attribute) plot_train_stats() (in module jax_agents.common.plotting)

Q

q_net (jax_agents.algorithms.ddpg.DDPGFunc attribute) q_net_size (jax_agents.algorithms.ddpg.DDPGConfig attribute)

q_opt_state (jax_agents.algorithms.ddpg.DDPGState attribute) q_optimizer (jax_agents.algorithms.ddpg.DDPGFunc attribute) q_params (jax_agents.algorithms.ddpg.DDPGState attribute)

R

render() (jax_agents.environments.pendulum.PendulumEnv method) render_csv() (in module jax_agents.common.simulation) ReplayBuffer (class in jax_agents.common.data_processor)

rescale_action() (jax_agents.environments.pendulum.PendulumEnv method) reset() (jax_agents.environments.pendulum.PendulumEnv method) reward_func() (jax_agents.environments.pendulum.PendulumEnv method) runge_kutta() (in module jax_agents.common.runge_kutta)

S

sample_batch() (jax_agents.common.data_processor.ReplayBuffer method) seed (jax_agents.algorithms.ddpg.DDPGConfig attribute) (jax_agents.common.training.TrainConfig attribute) select_action() (jax_agents.algorithms.ddpg.DDPG method) SimLogger (class in jax_agents.common.simulation)

simulate() (in module jax_agents.common.simulation) state_dim (jax_agents.algorithms.ddpg.DDPGConfig attribute) (jax_agents.algorithms.ddpg.DDPGFunc attribute) step() (jax_agents.environments.pendulum.PendulumEnv method) store() (jax_agents.common.data_processor.ReplayBuffer method)

T

train() (in module jax_agents.common.training)

train_step() (jax_agents.algorithms.ddpg.DDPG method) TrainConfig (class in jax_agents.common.training)